{"paper":{"title":"Offline-First LLM Architecture for Adaptive Learning in Low-Connectivity Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Offline-first LLM architecture runs quantized models locally to deliver adaptive, curriculum-aligned explanations on legacy hardware without internet.","cross_cats":["cs.AR","cs.CL","cs.HC"],"primary_cat":"cs.CY","authors_text":"Ann Move Oguti, Joseph Walusimbi, Joshua Benjamin Ssentongo, Keith Ainebyona","submitted_at":"2026-02-14T09:53:40Z","abstract_excerpt":"Artificial intelligence (AI) and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalized explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aw"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results show stable operation on legacy hardware, acceptable response times, and positive user perceptions regarding support for self-directed learning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That quantized LLMs running locally can generate accurate, curriculum-aligned explanations at adjustable complexity levels that are educationally effective without cloud support or additional fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An offline-first architecture using quantized LLMs and hardware-aware selection provides curriculum-aligned, level-adaptive tutoring on CPU-only devices in low-connectivity settings.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Offline-first LLM architecture runs quantized models locally to deliver adaptive, curriculum-aligned explanations on legacy hardware without internet.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9cc5ae4b3e18b4740c3b42ee130dd3b21b5bb9d5797f138f67b46ab588b8177a"},"source":{"id":"2603.03339","kind":"arxiv","version":6},"verdict":{"id":"b77dffa3-9035-48d3-afc1-0e165c66fd11","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T22:31:56.001204Z","strongest_claim":"Results show stable operation on legacy hardware, acceptable response times, and positive user perceptions regarding support for self-directed learning.","one_line_summary":"An offline-first architecture using quantized LLMs and hardware-aware selection provides curriculum-aligned, level-adaptive tutoring on CPU-only devices in low-connectivity settings.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That quantized LLMs running locally can generate accurate, curriculum-aligned explanations at adjustable complexity levels that are educationally effective without cloud support or additional fine-tuning.","pith_extraction_headline":"Offline-first LLM architecture runs quantized models locally to deliver adaptive, curriculum-aligned explanations on legacy hardware without internet."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.03339/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}